Loading...
Loading...
Found 8 Skills
Synthesizes research findings into design decisions via codebase investigation. Use when (1) translating research into implementation approaches, (2) selecting between design alternatives, (3) executing after /research or deep-research, or (4) preparing input for /plan phase.
Automatically check and update folder-specific AGENTS.md during research. Before investigating a domain, read nearest AGENTS.md for existing context. After discovering valuable patterns, append learnings to that file.
Create implementation task plans in `_/local-plans/<plan-name>.md`. First investigate the codebase using the Explore Agent, then document it in verifiable granularity and parallel-executable units, following the standard format (Background & Purpose, Current Status, Design, File Structure Tree, Implementation Steps, Verification Methods) that can be validated by the plan-verifier Agent. Used for requests like "Make a plan", "Design", "Task decomposition", "Think about implementation approach". plan, planning, design, implementation plan, task decomposition, create-plan
Turn a GitHub issue into an implementation plan — investigate the codebase, propose an approach, list critical files and changes, outline test strategy. Use when user says 'plan this issue', 'what's the approach for', 'how would I tackle', 'implementation plan for', or 'before coding'. Do NOT use for actually implementing (write the code directly after the plan) or for breaking a too-large issue into sub-issues (use splice-issue).
Use when thinking through ideas, investigating problems, or clarifying requirements — before or during a Beat change
Explore and investigate ideas before committing to a change. Trigger: When the orchestrator launches you to think through a feature, investigate the codebase, or clarify requirements.
Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.
Technical Research - investigates the codebase and builds a catalogue of solution variants per problem area. Iterative — can be re-run to widen the catalogue. Does not make decisions; selection happens in spec:design.